Search Results for author: Xiangyang Liu

Found 14 papers, 9 papers with code

Can AI Assistants Know What They Don't Know?

1 code implementation24 Jan 2024 Qinyuan Cheng, Tianxiang Sun, Xiangyang Liu, Wenwei Zhang, Zhangyue Yin, ShiMin Li, Linyang Li, Zhengfu He, Kai Chen, Xipeng Qiu

To answer this question, we construct a model-specific "I don't know" (Idk) dataset for an assistant, which contains its known and unknown questions, based on existing open-domain question answering datasets.

Math Open-Domain Question Answering +1

Flames: Benchmarking Value Alignment of LLMs in Chinese

1 code implementation12 Nov 2023 Kexin Huang, Xiangyang Liu, Qianyu Guo, Tianxiang Sun, Jiawei Sun, Yaru Wang, Zeyang Zhou, Yixu Wang, Yan Teng, Xipeng Qiu, Yingchun Wang, Dahua Lin

The widespread adoption of large language models (LLMs) across various regions underscores the urgent need to evaluate their alignment with human values.

Benchmarking Fairness

Federated Prompting and Chain-of-Thought Reasoning for Improving LLMs Answering

no code implementations27 Apr 2023 Xiangyang Liu, Tianqi Pang, Chenyou Fan

Due to the unsatisfactory accuracy of LLMs' zero-shot prompting with standalone questions, we propose to improve the distributed synonymous questions using Self-Consistency (SC) and Chain-of-Thought (CoT) techniques.

Mathematical Reasoning

Late Prompt Tuning: A Late Prompt Could Be Better Than Many Prompts

1 code implementation20 Oct 2022 Xiangyang Liu, Tianxiang Sun, Xuanjing Huang, Xipeng Qiu

Through extensive experimental results across various tasks and PTMs, we show that LPT can achieve competitive performance to full model tuning and other PETuning methods under both full-data and few-shot scenarios while possessing faster training speed and lower memory cost.

A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation

1 code implementation Findings (ACL) 2022 Tianxiang Sun, Xiangyang Liu, Wei Zhu, Zhichao Geng, Lingling Wu, Yilong He, Yuan Ni, Guotong Xie, Xuanjing Huang, Xipeng Qiu

Previous works usually adopt heuristic metrics such as the entropy of internal outputs to measure instance difficulty, which suffers from generalization and threshold-tuning.

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline

1 code implementation NAACL 2022 Xiangyang Liu, Tianxiang Sun, Junliang He, Jiawen Wu, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu

ELUE is dedicated to depict the Pareto Frontier for various language understanding tasks, such that it can tell whether and how much a method achieves Pareto improvement.

Paradigm Shift in Natural Language Processing

1 code implementation26 Sep 2021 Tianxiang Sun, Xiangyang Liu, Xipeng Qiu, Xuanjing Huang

In this paper, we review such phenomenon of paradigm shifts in recent years, highlighting several paradigms that have the potential to solve different NLP tasks.

Chunking NER +3

A Survey of Transformers

1 code implementation8 Jun 2021 Tianyang Lin, Yuxin Wang, Xiangyang Liu, Xipeng Qiu

X-formers) have been proposed, however, a systematic and comprehensive literature review on these Transformer variants is still missing.

Early Exiting with Ensemble Internal Classifiers

no code implementations28 May 2021 Tianxiang Sun, Yunhua Zhou, Xiangyang Liu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu

In this paper, we show that a novel objective function for the training of the ensemble internal classifiers can be naturally induced from the perspective of ensemble learning and information theory.

Ensemble Learning

Low Bit-Rate Wideband Speech Coding: A Deep Generative Model based Approach

no code implementations4 Feb 2021 Gang Min, Xiongwei Zhang, Xia Zou, Xiangyang Liu

Traditional low bit-rate speech coding approach only handles narrowband speech at 8kHz, which limits further improvements in speech quality.


A Hypergraph-Partitioned Vertex Programming Approach for Large-scale Consensus Optimization

no code implementations30 Aug 2013 Hui Miao, Xiangyang Liu, Bert Huang, Lise Getoor

In modern data science problems, techniques for extracting value from big data require performing large-scale optimization over heterogenous, irregularly structured data.

hypergraph partitioning

Cannot find the paper you are looking for? You can Submit a new open access paper.